diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2015-02-26 09:19:26 +0100 |
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2015-02-26 09:19:26 +0100 |
| commit | 63a562f95ee62e05e689bf7fbf8e923749248b05 (patch) | |
| tree | 347ce60caa8c3ab98500b8534493ee9726e34bdd | |
| parent | 5c340b038740061c61f55be1935e364a883a3138 (diff) | |
[escapist] Detect IP blocking and use another UA (Fixes #5069)
| -rw-r--r-- | youtube_dl/extractor/escapist.py | 18 |
1 files changed, 15 insertions, 3 deletions
diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index b45c1dbd0..80e9084f4 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..compat import ( compat_urllib_parse, + compat_urllib_request, ) from ..utils import ( ExtractorError, @@ -12,6 +13,7 @@ from ..utils import ( class EscapistIE(InfoExtractor): _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])' + _USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko' _TEST = { 'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate', 'md5': 'ab3a706c681efca53f0a35f1415cf0d1', @@ -28,7 +30,9 @@ class EscapistIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage_req = compat_urllib_request.Request(url) + webpage_req.add_header('User-Agent', self._USER_AGENT) + webpage = self._download_webpage(webpage_req, video_id) uploader_id = self._html_search_regex( r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'", @@ -54,9 +58,11 @@ class EscapistIE(InfoExtractor): formats = [] ad_formats = [] - def _add_format(name, cfgurl, quality): + def _add_format(name, cfg_url, quality): + cfg_req = compat_urllib_request.Request(cfg_url) + cfg_req.add_header('User-Agent', self._USER_AGENT) config = self._download_json( - cfgurl, video_id, + cfg_req, video_id, 'Downloading ' + name + ' configuration', 'Unable to download ' + name + ' configuration', transform_source=js_to_json) @@ -74,6 +80,9 @@ class EscapistIE(InfoExtractor): 'url': p['url'], 'format_id': name, 'quality': quality, + 'http_headers': { + 'User-Agent': self._USER_AGENT, + }, }) _add_format('normal', config_url, quality=0) @@ -85,6 +94,9 @@ class EscapistIE(InfoExtractor): pass # That's fine, we'll just use normal quality self._sort_formats(formats) + if '/escapist/sales-marketing/' in formats[-1]['url']: + raise ExtractorError('This IP address has been blocked by The Escapist', expected=True) + res = { 'id': video_id, 'formats': formats, |